读取网页内容

 c#读取网页内容

 public static class Internet
    {
        private static HttpWebRequest request;
        private static HttpWebResponse response;
        private static StreamReader reader;
        private static string strResults;
        private static Encoding encoding;
        static Internet()
        {
            strResults = string.Empty;
        }
        public static string GetHtml(string strLink)
        {

            try
            {

                request = (HttpWebRequest)WebRequest.Create(strLink);
                switch ((DateTime.Now.Second % 2))
                {
                    case 0:
                        request.UserAgent = "Mozilla/5.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1;.NET CLR 2.0.50727)";
                        break;

                    default:
                        request.UserAgent = "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.2; .NET CLR 1.1.4322; .NET CLR 2.0.50727; InfoPath.1) Web-Sniffer/1.0.24";
                        break;
                }
                response = (HttpWebResponse)request.GetResponse();

                if (response.CharacterSet != null && response.CharacterSet.ToLower() == "utf-8")
                {
                    encoding = Encoding.UTF8;
                }
                else
                {
                    encoding = Encoding.GetEncoding(936);
                }
                reader = new StreamReader(response.GetResponseStream(), encoding);
                strResults = Regex.Replace(reader.ReadToEnd(), @"[\r\n]", " ");
                if (strLink != response.ResponseUri.ToString())
                {
                    strResults = "|RedirectWeb|" + strResults;
                }
                return strResults;
            }
            catch
            {
                return string.Empty;
            }
            finally
            {
                request.Abort();
                if (response != null)
                {
                    response.Close();
                }
                if (reader != null)
                {
                    reader.Close();
                    reader.Dispose();
                }
            }

        }
    }

java 读取网页内容

public static String getPageContent(String strUrl, String strPostRequest,
            int maxLength) throws Exception {
        //读取结果网页
        StringBuffer buffer = new StringBuffer();
        System.setProperty("sun.net.client.defaultConnectTimeout", "5000");
        System.setProperty("sun.net.client.defaultReadTimeout", "5000");
        try {
            URL newUrl = new URL(strUrl);
            HttpURLConnection hConnect = (HttpURLConnection) newUrl
                    .openConnection();
            //POST方式的额外数据
            if (strPostRequest.length() > 0) {
                hConnect.setDoOutput(true);
                OutputStreamWriter out = new OutputStreamWriter(hConnect
                        .getOutputStream());
                out.write(strPostRequest);
                out.flush();
                out.close();
            }
            //读取内容

            BufferedReader rd = new BufferedReader(new InputStreamReader(hConnect.getInputStream()));
            int ch;
            for (int length = 0; (ch = rd.read()) > -1 && (maxLength <= 0 || length < maxLength); length++) {
                buffer.append((char) ch);
            }
            rd.close();
            hConnect.disconnect();
            return buffer.toString().trim();
        } catch (Exception e) {
            // return "错误:读取网页失败！";
            return null;
        }
    }